摘要
电力变压器是变电站的关键设备,其运行的安全、可靠性直接关系到电力系统的安全与稳定。因此,有效地监测变压器运行状态、诊断和预报变压器故障具有实际意义。
本文在广泛查阅相关文献的基础上,系统了解了电力变压器故障过程特征气体产生的物、化机理,以及不同种类故障与不同种类特征气体含量之间的相应关系,以及相应的检测方法和故障属性分类技术。结合工作实际,本文的主要工作如下:
(1)在分析了油中溶解气体含量与不同故障之间联系的基础上,利用油中特征气体含量数据样本作为人工神经网络学习训练的特征向量矩阵,充分利用人工神经网络具有的并行处理、学习和记忆、非线性映射、自适应能力和鲁棒性等特点,构造了基于人工神经网络的电力变压器故障特征气体诊断系统,选择和训练了适用于电力变压器运行状态及其故障在线监测、诊断的BP、RBF神经网络,对网络的结构、优化和算法进行了探讨,应用MATLAB中的NNTOOL工具箱进行了仿真试验,比较分析了各种不同类型神经网络的性能和故障诊断的准确率。
(2)基于D-S证据理论的特征级信息融合。详细介绍了证据理论的基本原理、合成规则、推理过程,建立了基于证据理论的信息融合故障诊断方法,并论述了诊断的具体实现。
(3)针对神经网络和D-S证据理论在变压器故障诊断的运用过程中存在不合理处,引用了一种新的计算Mass函数的算法,该算法依据证据体可信度因素和证据体与目标关联的相对熵来分配证据体的Mass函数,较全面反映了证据体的不确定性。将此方法与神经网络进行有机结合提出了一种神经网络与改进的D-S证据理论融合的变压器故障综合诊断方法。详细介绍了该方法的原理和具体实施步骤。最后通过实例证明,该方法具有较高的诊断准确性和可靠性。
(4)分析了几种变压器故障诊断模型的有效性,并通过大量的实例分析表明,应用本文提出的模型所获得的诊断准确率高于单一的诊断方法的诊断结果,该算法具有较高的检测准确率,在电力变压器故障诊断中有良好的应用前景。
(5)论文最后对上述研究成果进行了总结,提出了进一步研究的方向。
Power transformer is the key apparatus at the transformer substation, its working safe and reliability relate to the safety and stabilization of power system directly. So it is important to study the electric power equipments' condition monitoring and fault diagnosis.
This paper is based on a lot of references, system overview the fault processing of the power transformer, the principle of generation characteristic gas, corresponding relationship between the different kinds of fault and different kinds of characteristic gas content and detection method and fault attribute classification technology. Combining the actual work, the main work is as follows:
(1) Based on the relationship between the dissolving gas content in oil and different fault types, analyze the sample data of the gas content in oil. Then these data samples become to the learning and training characteristic vector matrix of the artificial neural network. Making the most of the paralleling processing, learning, memorization, nonlinearity mapping, adaptation ability and robustness etc of the artificial neural network, constructing the fault characteristic gas diagnosis system of the power transformer based on the artificial neural network. Selecting and training the BP and RBP neural network which suitable to the power transformer running condition and fault on-line detection, diagnosis and forecasting. We have discussed the network construction, optimization and algorithmic, and we have done the simulation experiment by the NNTOOL in the Matlab. Then studied and solved method has put forward in this paper. The main content to study is definite. Through the comparative of each different type neural network's performance and fault diagnosis's rate of accuracy, it determined the suitable neural network model in the transformer insulation failure diagnosis.
(2) Information fusion on characteristic level based on D-S evidence theory: the basic Principle, formatting rule, reasoning Process of evidence theory are introduced in detail. A method of fault diagnosis based on evidence theory and information fusion is Proposed and expounded about how to realize the fault diagnosis system.
(3)Evidence theory and neural network are widely used in data fusion systems. However, there exist some problems in its combination rule. This paper quoted a new algorithm for assigning Mass function. This algorithm determines the uncertainty of the bodies of evidence, which combines the reliability of the bodies of evidence and the entropy of associated coefficient between the evidences and the targets. It also generally reflects the total uncertainty of the evidences. Directly toward the algorithm, this paper proposed a new synthetic method of transformer fault diagnosis, which based on the neural networks and D-S evidence theory.
(4) Analyzing the effectiveness of a number of transformer fault diagnosis model. The analysis of a large number of examples show that the diagnostic accuracy of the model proposed in this paper was higher than a single diagnostic model, the algorithm has high detection accuracy in the power transformer fault diagnosis. And it has a good application prospects.
(5) The above research results are summarized finally. The further investigative direction is put forward in the end.
引文
[1]王楠,律方成,刘云鹏等.基于粗糙集理论与模糊Petri网络的油浸式电力变压器综合故障诊断[J].中国电机工程学报,2003,23(12):127-132
[2]陈家斌.电气设备故障检测诊断方法及实例,第1版.北京:中国水利水电出版社,2003,11-12
[3]刘英肖.利用油中溶解气体特征诊断变压器内部故障.华北电力技术,1999(27):27
[4]孙才新,陈伟根,李俭等编著.电气设备油中气体在线监测与故障诊断技术,第1版.北京:科学出版社.2003,47-49
[5]毕为民.变压器局部放电监测中以小波包去噪和统计量识别放电模式的研究(博士学位论文).重庆:重庆大学电气学院.2003,6-8
[6]陈化钢.电力设备预防性试验方法及诊断技术,第1版.北京:中国科学技术出版社,2001,170-171
[7]Zhenyuan Wang,Yilu Liu,GhffinP.J.Artificial intelligence in OLTC fault diagnosis using dissolved gas-in-oil information.IEEE Power Engineering Society Summer Meeting,2000,4(7):2422-2427
[8]Zhenyuan Wang,Yihi Liu,Nien-Chung Wang.Artificial intelligence in Power equipment fault diagnosis.IEEE Power Engineering Society Winter Meeting,2000,1(1):128-133
[11]Zhenyuan Wang,Yilu Liu,Griffin,P.J.Neural net and expert system diagnose transformer faults.IEEE Computer Applications in Power,2000,130):50-55
[9]C.R.Frak,J.L.Young.Unsupervised Feature Selection Using A Fuzzy-Genetic Algorithm,IEEE Intemational Fuzzy Systems Conference Proceedings,1999(8),1111267-1269
[10]王旭,王宏.人工神经元网络原理与应用[M].东北大学出版社.2000
[11]袁曾任.人工神经元网络及其应用[M].北京:清华大学出版社,1999
[12]Thang,K.F.Aggarwal,R.K.Esp,D.G.McGrail.A.J.Statistical and neural network analysis of dissolved gases in power transformers.Dielectric Materials[C]. Measurements and Applications,2000.Eighth International Conference on(IEE Conf.Publ.No.473),2000,Page(s):324-329
[13]黄鞠铭,朱子述,胡文华.BP网络在基于DGA变压器故障诊断中的应用[J].高电压技术,1996,22(2):21-24
[14]Y.M.Tu,Y.S.Quan,Z.Yan.Transformer Fault Diagnosis Based on Artificial Neural Network.Proceedings of Joint Conference:1996 Asisn International Conference On Dielectrics & Electrical Insulation.4~(th) Japan-China Conference on Electrical insulation Diagnosis.1996,Xi'an,393-396
[15]李天云,应鸿等,基于局部特征量的神经元网络方法在变压器故障诊断中的应用,电网技术1996,20(11):51-54
[16]丁晓群,Liu Y等.神经网络应用于电力变压器故障诊断.电力系统自动化,1996,20(2):24-27
[17]徐文,王大忠等.人工神经网络在变压器特征气体诊断中的应用.高电压技术1996,22(2):27-30
[18]徐文,王大忠,周泽存.结合遗传算法的人工神经网络在电力变压器故障诊断中的应用[J].中国电机工程学报,1997,17(2):109-112
[19]D.Wenzel,H.Borsi,E.Gockenhach,et al A New Approach for Partial Discharge Recognition on Transformer On-site by means of Genetic Algorithms.Conference Record of the 1996 IEEE International Symposium on Electrical Insulation 1996,Canada,57-60
[20]槐喜斌.多信息融合技术在汽轮机转子故障诊断中的应用研究[D].哈尔滨工业大学硕士论文,2003
[21]夏虹.基于数据融合技术的设备故障诊断方法研究[D].哈尔滨工程大学博士论文,2000
[22]臧宏志.基于信息融合的大型电力变压器故障诊断[D].山东大学硕士论文,2002
[23]张兆礼.神经网络数据融合算法研究[D].哈尔滨工业大学博士论文,2001
[24]吴艳.多传感器数据融合算法研究[D].西安电子科技大学博士论文,2003
[25]I.O.Kozine,YV.Filimonov.Imprecise reliabilities:experiences and advances[J].Reliability Engineering and System Safety.2000,67:75-83.
[26]Ronald R.Yager.Modeling uncertainty using partial information[J].Information Sciences.1999,121:271-294.
[27]Mark J.Ducey.Representing uncertainty in silvicultural decisions:an application of the Dempster-Shafer theory of evidence[J].Forest Ecology and Management.2001,150:199-211.
[28]李芳社,王宝树.神经网络技术在数据融合中的应用[J].西安电子科技大学学报,1998,25(6):790-793
[29]张兆礼,孙圣和.假设检验中Neyman-Pearson准则的神经网络实现新算法[J].哈尔滨工业大学学报,2001,33(1):48-51
[30]Dasarathy B V Sensor fusion potential exploitation-innovative architecture and illustrative application[J].Proceedings of the IEEE,1997,85(1):29-36.
[31]Torfinn Taxt,Anne H.Schustas Solberg.Information fusion in remote sensing[J].Pergamon,1997,41(3):337-342
[32]李宏,徐晖.基于人工神经网络与证据理论相结合的信息融合空间点目标识别方法研究[J].信息与控制,1997,26(2):151-155
[33]李宏,刘江涛.主观Bayes方法与神经网络相结合的多传感器数据融合空间点目标识别方法[J].红外与毫米波学报,1997,16(6):448-454
[34]陶然,周开利.基于神经网络数据融合空间点目标识别方法[J].系统工程与电子技术,2000,22(11):42-45
[35]刘宜平,沈毅.一种基于多级信息融合技术的系统故障诊断方法[J].系统工程与电子技术,2000,22(12):97-100
[36]梁继民,杨万海.决策融合的模糊积分方法[J].西安电子科技大学学报,1998,25(2):250-253
[37]袁小宏,屈梁生.机械故障诊断中的信息融合利用问题研究[J].振动、测试与诊断,1999,19(3):187-192
[38]V.Dasarathy.Fuzzy evidential reasoning approach to target identity and state fusion in multisensor environments[J].Optical Engineering,1997.36(3):669-683.
[39]温熙森,秦国军.大型复杂机电设备监测诊断体系结构研究[J].中国机械工程,1997,8(2):99-102
[40]刚铁,吴林.超声检测中的多源信息融合技术与缺陷识别[J].机械工程学报,1999,35(2):11-14
[41]张彦铎,姜兴渭.多传感器信息融合及在智能故障诊断中的应用[J].传感器技术,1999,18(2):18-22
[42]刘同明等.数据融合技术及其应用.国防工业出版社.1998:1-13
[43]Durrant-Whyte.Sensor models and multisensor integration.Joumal of Roboties Research.1988,7(6):97-113
[44]涂小强.信息融合的原理与方法概述.电讯技术.1999,(3):1-6
[45]Thang,K.F.Aggarwal,R.K.Esp,D.G.McGrail,A.J.Statistical and neural network analysis of dissolved gases in power transformers.Dielectric Materials[C].Measurements and Applications,2000.Eighth International Conference on(IEE Conf.Publ.No.473),2000 Page(s):324-329
[46]杨启平,薛五德,蓝之达.基于人工神经网络的变压器故障诊断[J].变压器,2000,37(3):33-36
[47]钱政,高文胜,尚勇.用可靠性数据分析及BP网络诊断变压器故障[J].高电压技术,1999,25(1):13-15
[48]钱政,严璋.结合多元统计分析的神经网络在变压器故障诊断中的应用[J].变压器,2000,37(4):32-35
[49]徐大可,李彦明.人工神经网络在变压器绕组变形诊断中的应用[J].高电压技术,1998,24(3):21-23
[50]王伟.人工神经网络—入门与应用.北京航空航天大学出版社.1995
[51]焦李成.神经网络系统理论.西安电子科技大学出版社.1990
[52]Barron.A.R.APProximation and estimation bounds for artificial neural networks.Machine Learing.1994,14:115-133
[53]袁曾任.人工神经元网络及其应用[M].北京:清华大学出版社,1999.
[54]A.P Dempster.Upper and Lower Probabilities Induced by a Multivalued Mapping.Annals of Mathematical Statisties.1967,38;325-339
[55]A.P.Dempster.A Generalization of Bayesian Inference.Journal of the Royal Statistical Soeiety.1968,30:205-247
[56]段新生.证据理论与决策、人工智能.北京:中国人民大学出版社,1993:13-36
[57]LouRenC,KAYMiehaelG.Multi—sensorintegrationandfusioninintelligentsystems.IEEE TransactionSonSystems,ManandCybemeties.1989,19(5):901-903.
[58]BoglerPhiliPL·Shafe—DemPsterreasoningwithapPlicationtomulti—sensorta很etidentifieation systems.IEEEtransactionsonsystems,Manandc沙emeties.1989,17(6):901-930.
[59]李宏坤.基于多征兆D—S证据理论的柴油机融合诊断(博士学位论文).大连:大连理工大学电气学院.2003.9
[60]倪国强,梁好臣.基于Dempster—Shafer证据理论的数据融合技术研究.北京理工大学学报,2001,26(3):6-10
[61]邱大庆,周亚明,王锐,赵振兵,基于D-S证据理论的油浸式电力变压器故障诊断,[J],电力科学与工程,2007,23(1):28-32
[62]胡汉梅,鲍亮亮,赵海军.神经网络在变压器故障诊断中典型算法研究.高压电器.2008,44(3):217-220
[63]吴开贵,王韶,张安邦等.基于RBF神经网络的电网可靠性评估模型研究[J].中国电机工程学报,2000,20(6):9-12.
[64]戴冠中,潘泉,张山鹰等.证据推理的进展及存在问题[J].控制理论与应用,1999,16(3):465-469
[65]廖瑞金,廖玉祥,杨丽君等.多神经网络与证据理论融合的变压器故障综合诊断方法研究[J].中国电机工程学报,2006,26(3):121-124
[66]周志华,尹旭日,陈兆乾。等.神经网络在电力变压器运行状态检测中的应用[J].自动化学报,2002,28(2):301-305
[67]江四厚,王汉功,阳能军.基于熵的Mass函数算法及在液压泵故障诊断中的应用.2007,35(12):185-188